Automatic volume control based on speech recognition
An entertainment system suitable for use in a vehicle and configured to control an output volume of the system includes a microphone and a processor. The microphone is configured to detect sound in a cabin of the vehicle, and output a microphone signal indicative of the sound. The processor is configured to determine a difference signal based on a difference between the microphone signal and an output signal corresponding to sound being output by the system, determine if the difference signal corresponds to human speech, and decrease the output volume of the system when the difference signal corresponds to human speech.
1. An entertainment system suitable for use in a vehicle, said system configured to control an output volume of the system, said system comprising:
a microphone configured to detect sound in a cabin of the vehicle, and output a microphone signal indicative of the sound;
a processor configured to determine a difference signal based on a difference between the microphone signal and an output signal corresponding to sound being output by the system, determine if the difference signal corresponds to human speech, and decrease the output volume of the system when the difference signal corresponds to human speech, determine a difference magnitude of the difference signal if the difference signal does not correspond to human speech, and increase the output volume of the system when the difference signal does not correspond to human speech and the difference magnitude is greater than a difference threshold.
2. The system in accordance with claim 1 , wherein the processor is further configured to increase the output volume to a previous level a delay time after the difference signal indicates that human speech has stopped.
3. A method for controlling an output volume of an entertainment system suitable for use in a vehicle, said method comprising the steps of:
receiving a microphone signal from a microphone configured to detect sound in a cabin of the vehicle;
determining a difference signal based on a difference between the microphone signal and an output signal corresponding to sound being output by the system, wherein the sound being output by the system is characterized by an output volume;
determining if the difference signal corresponds to human speech; and
decreasing the output volume of the system when the difference signal corresponds to human speech;
determining a difference magnitude of the difference signal if the difference signal does not correspond to human speech; and
increasing the output volume of the system when the difference signal does not correspond to human speech and the difference magnitude is greater than a difference threshold.
4. The method in accordance with claim 2 , wherein the method further comprises the step of
increasing the output volume to a previous level a delay time after the difference signal indicates that human speech has stopped.